VIEW 1

Analytical Question: How do age and gender vulnerability patterns for different infectious causes compare between Europe and the rest of the world, and how have these patterns evolved over time?

import altair as alt
import pandas as pd
import numpy as np
alt.data_transformers.enable("vegafusion")

DataTransformerRegistry.enable('vegafusion')

df = pd.read_csv("../data1.csv")
# df.age.unique()
df

	Area Code	location	Unit	measure	sex	age	cause	metric	year	mortality_value	upper_CI	lower_CI	pesticide_tonnes	% of GDP	mortality_class	region_type
0	5500	Oceania	kg/cap	Deaths	Female	25+ years	Sepsis and Inf.	Number	2018	0.115895	0.175355	0.074152	2.06	NaN	low end	Non-Europe
1	5501	Oceania	kg/cap	Deaths	Female	25+ years	Sepsis and Inf.	Number	2018	0.115895	0.175355	0.074152	2.84	NaN	low end	Non-Europe
2	5502	Oceania	kg/cap	Deaths	Female	25+ years	Sepsis and Inf.	Number	2018	0.115895	0.175355	0.074152	0.17	NaN	low end	Non-Europe
3	5504	Oceania	kg/cap	Deaths	Female	25+ years	Sepsis and Inf.	Number	2018	0.115895	0.175355	0.074152	0.98	NaN	low end	Non-Europe
4	5500	Oceania	kg/cap	Deaths	Female	<20 years	Sepsis and Inf.	Number	2018	0.004698	0.007462	0.002894	2.06	NaN	low end	Non-Europe
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
32331	5404	Western Europe	kg/cap	Deaths	Female	25+ years	Gonococcal Inf.	Number	2023	8.607440	10.822334	6.696607	0.63	NaN	low end	Non-Europe
32332	5404	Western Europe	kg/cap	Deaths	Male	<20 years	Gonococcal Inf.	Number	2023	0.029280	0.039035	0.021389	0.63	NaN	low end	Non-Europe
32333	5404	Western Europe	kg/cap	Deaths	Female	<20 years	Gonococcal Inf.	Number	2023	0.080631	0.099697	0.066684	0.63	NaN	low end	Non-Europe
32334	5404	Western Europe	kg/cap	Deaths	Male	55+ years	Gonococcal Inf.	Number	2023	0.883928	1.233798	0.642922	0.63	NaN	low end	Non-Europe
32335	5404	Western Europe	kg/cap	Deaths	Female	55+ years	Gonococcal Inf.	Number	2023	7.413664	9.356024	5.630986	0.63	NaN	low end	Non-Europe

32336 rows × 16 columns

#binning ages into 3 categories
age_map = {
    "<1 year": "Children",
    "<5 years": "Children",
    "<20 years": "Children",
    "25+ years": "Adults",
    "55+ years": "Older Adults",
    "70+ years": "Older Adults",
    "All ages": None
}
df["age_group"] = df["age"].map(age_map)

df["mortality_log"] = np.log10(df["mortality_value"].replace(0, np.nan))

master = df[[
    "year", "region_type", "sex", "age_group", "cause", "mortality_value"
]].copy()

data_sex = master[master["sex"].isin(["Male","Female"])]
data_age = (
    master.groupby(["year", "age_group", "sex", "region_type"], as_index=False)
          .agg({"mortality_value": "mean"})
)

data_age = data_age[data_age["age_group"]!= "All ages"]
data_agg = (
    master.groupby(["age_group","cause","region_type"], as_index=False)
          .agg({"mortality_value": "mean"})
)

# Parameters and selections
region_param = alt.param(
    name="region_param",
    bind=alt.binding_select(
        options=["Europe", "Non-Europe"],
        name="Region: "
    ),
    value="Europe"
)

cause_select = alt.selection_point(fields=["cause"])

# Line chart
line = (
    alt.Chart(data_age)
    .add_params(region_param)
    .transform_filter(alt.datum.region_type == region_param)
    .mark_line(point=True)
    .encode(
        x=alt.X("year:O", title="Year"),
        y=alt.Y("mortality_value:Q", title="Mortality Value"),
        color=alt.Color(
            "sex:N",
            scale=alt.Scale(
                domain=["Female", "Male"],
                range=["#ff4fa3", "#4a90e2"]
            )
        ),
        facet=alt.Facet("age_group:N", columns=3)  
    )
    .properties(width=220, height=180)
    .properties(title="Mortality Trends by Age Group")
).resolve_scale(y='independent')

# Bubble chart
bubble = (
    alt.Chart(data_agg)
    .mark_circle(opacity=0.8, stroke="black", strokeWidth=1)
    .encode(
        x=alt.X("cause:N", title="Cause", axis=alt.Axis(labelAngle=-45)),
        y=alt.Y("age_group:N", title="Age Group"),
        size=alt.Size("mortality_value:Q", scale=alt.Scale(range=[100, 1000]), 
                      title="Mortality"),
        color=alt.condition(
            cause_select,
            alt.value("steelblue"),
            alt.value("lightgray")
        ),
        tooltip=["cause:N", "age_group:N", alt.Tooltip("mortality_value:Q", format=".2f")]
    )
    .transform_filter(alt.datum.region_type == region_param)
    .add_params(cause_select)
    .properties(width=400, height=300, title="Cause × Age Group (Click to Filter)")
)

# Density chart
density = (
    alt.Chart(data_sex)
    .transform_filter(alt.datum.region_type == region_param,alt.datum.mortality_value < 20000)
    .transform_filter(cause_select)
    .transform_density(
        "mortality_value",
        groupby=["sex"],
        as_=["mortality_value", "density"]
    )
    .mark_area(opacity=0.5)
    .encode(
        x=alt.X("mortality_value:Q", title="Mortality Value"),
        y=alt.Y("density:Q", title="Density"),
        color=alt.Color(
            "sex:N",
            scale=alt.Scale(
                domain=["Female", "Male"],
                range=["#ff4fa3", "#4a90e2"]
            ),
            title="Sex"
        )
    )
    .properties(width=400, height=300, title="Mortality Distribution by Sex")
)

# Combine into dashboard
dashboard = line & (density | bubble)
dashboard